INDEX

Explanations

phrases related to organizations and institutions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.15

fall

-0.15

 merely

-0.14

ÙĬÙĬÙĨ

-0.14

hon

-0.14

Ð

-0.13

hard

-0.13

inia

-0.13

Ub

-0.13

eer

-0.13

POSITIVE LOGITS

 ########.

0.16

amp

0.15

lt

0.15

tml

0.15

íķĻê¸°

0.14

istory

0.14

dash

0.14

Ø§Ø¦ÙĤ

0.14

andom

0.14

quot

0.14

Activations Density 0.002%

phrases related to organizations and institutions

No Comments

No Known Activations